Adaptive Multi-Task Transfer Learning for Chinese Word Segmentation in Medical Text
Chinese word segmentation (CWS) trained from open source corpus faces dramatic performance drop when dealing with domain text, especially for a domain with lots of special terms and diverse writing styles, such as the biomedical domain. However, building domain-specific CWS requires extremely high annotation cost. In this paper, we propose an approach by exploiting domain-invariant knowledge from high resource to low resource domains. Extensive experiments show that our model achieves consistently higher accuracy than the single-task CWS and other transfer learning baselines, especially when there is a large disparity between source and target domains.
Code (1)
Tasks
Chinese Word SegmentationTransfer LearningSimilar Papers 제목 키워드 기반
Incorporating Sememes into Chinese Definition Modeling
Chinese definition modeling is a challenging task that generates a dictionary definition in Chinese for a given Chinese word. To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which cont…
A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation
Word-level information is important in natural language processing (NLP), especially for the Chinese language due to its high linguistic complexity. Chinese word segmentation (CWS) is an essential task for Chinese downst…
Chinese Word SegmentationSegmentationTransfer LearningAdversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism
Named entity recognition (NER) is an important task in natural language processing area, which needs to determine entities boundaries and classify them into pre-defined categories. For Chinese NER task, there is only a v…
Chinese Named Entity RecognitionChinese Word Segmentationnamed-entity-recognitionNamed Entity Recognition+3Switch-LSTMs for Multi-Criteria Chinese Word Segmentation
Multi-criteria Chinese word segmentation is a promising but challenging task, which exploits several different segmentation criteria and mines their common underlying knowledge. In this paper, we propose a flexible multi…
Chinese Word SegmentationSegmentationA Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder
Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion. Previous work usually re…
Chinese Word SegmentationMulti-Task LearningSegmentation